© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229754
    Prev
    Next
    INDEX
    Explanations

    asking for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    $,
    0.51
    EXP
    0.43
    Flu
    0.42
    REAM
    0.42
    /
    0.41
    ନ୍
    0.40
    ραπε
    0.40
    緩
    0.40
    I
    0.39
    rines
    0.39
    POSITIVE LOGITS
     warranties
    0.50
     öğrenciler
    0.49
    btnInventory
    0.49
     Metallica
    0.44
     نمی‌
    0.43
    ไม่ใช่
    0.43
     sparring
    0.43
     quarterbacks
    0.43
     beslut
    0.42
     মেট্রোরে
    0.42
    Activations Density 0.000%

    No Known Activations